Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    politicians

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Expect
    -0.07
     guidance
    -0.07
     regulations
    -0.07
    \Migration
    -0.07
    interaction
    -0.07
     explanatory
    -0.07
    الأ
    -0.06
     california
    -0.06
     remar
    -0.06
     Responsible
    -0.06
    POSITIVE LOGITS
    手下
    0.07
    שמן
    0.07
    挫
    0.07
     liệt
    0.07
    楼
    0.07
     дв
    0.07
    괼
    0.07
     Moj
    0.07
    ------------↵
    0.06
    销量
    0.06
    Act Density 0.004%

    No Known Activations